metadata

license: cc-by-4.0
metrics:
  - bleu4
  - meteor
  - rouge-l
  - bertscore
  - moverscore
language: ru
datasets:
  - lmqg/qg_ruquad
pipeline_tag: text2text-generation
tags:
  - question generation
widget:
  - text: >-
      Нелишним будет отметить, что, развивая это направление, Д. И. Менделеев,
      поначалу априорно выдвинув идею о температуре, при которой высота мениска
      будет нулевой, <hl> в мае 1860 года <hl> провёл серию опытов.
    example_title: Question Generation Example 1
  - text: >-
      Однако, франкоязычный <hl> Квебек <hl> практически никогда не включается в
      состав Латинской Америки.
    example_title: Question Generation Example 2
  - text: >-
      Классическим примером международного синдиката XX века была группа
      компаний <hl> Де Бирс <hl> , которая в 1980-е годы контролировала до 90 %
      мировой торговли алмазами.
    example_title: Question Generation Example 3
model-index:
  - name: lmqg/mt5-base-ruquad-qg
    results:
      - task:
          name: Text2text Generation
          type: text2text-generation
        dataset:
          name: lmqg/qg_ruquad
          type: default
          args: default
        metrics:
          - name: BLEU4 (Question Generation)
            type: bleu4_question_generation
            value: 17.63
          - name: ROUGE-L (Question Generation)
            type: rouge_l_question_generation
            value: 33.02
          - name: METEOR (Question Generation)
            type: meteor_question_generation
            value: 28.48
          - name: BERTScore (Question Generation)
            type: bertscore_question_generation
            value: 85.82
          - name: MoverScore (Question Generation)
            type: moverscore_question_generation
            value: 64.56
          - name: BLEU4 (Question & Answer Generation (with Gold Answer))
            type: bleu4_question_answer_generation_with_gold_answer
            value: 19.28
          - name: ROUGE-L (Question & Answer Generation (with Gold Answer))
            type: rouge_l_question_answer_generation_with_gold_answer
            value: 52.09
          - name: METEOR (Question & Answer Generation (with Gold Answer))
            type: meteor_question_answer_generation_with_gold_answer
            value: 45.42
          - name: BERTScore (Question & Answer Generation (with Gold Answer))
            type: bertscore_question_answer_generation_with_gold_answer
            value: 90.95
          - name: MoverScore (Question & Answer Generation (with Gold Answer))
            type: moverscore_question_answer_generation_with_gold_answer
            value: 69.57
          - name: >-
              QAAlignedF1Score-BERTScore (Question & Answer Generation (with
              Gold Answer)) [Gold Answer]
            type: >-
              qa_aligned_f1_score_bertscore_question_answer_generation_with_gold_answer_gold_answer
            value: 91.1
          - name: >-
              QAAlignedRecall-BERTScore (Question & Answer Generation (with Gold
              Answer)) [Gold Answer]
            type: >-
              qa_aligned_recall_bertscore_question_answer_generation_with_gold_answer_gold_answer
            value: 91.09
          - name: >-
              QAAlignedPrecision-BERTScore (Question & Answer Generation (with
              Gold Answer)) [Gold Answer]
            type: >-
              qa_aligned_precision_bertscore_question_answer_generation_with_gold_answer_gold_answer
            value: 91.11
          - name: >-
              QAAlignedF1Score-MoverScore (Question & Answer Generation (with
              Gold Answer)) [Gold Answer]
            type: >-
              qa_aligned_f1_score_moverscore_question_answer_generation_with_gold_answer_gold_answer
            value: 70.06
          - name: >-
              QAAlignedRecall-MoverScore (Question & Answer Generation (with
              Gold Answer)) [Gold Answer]
            type: >-
              qa_aligned_recall_moverscore_question_answer_generation_with_gold_answer_gold_answer
            value: 70.04
          - name: >-
              QAAlignedPrecision-MoverScore (Question & Answer Generation (with
              Gold Answer)) [Gold Answer]
            type: >-
              qa_aligned_precision_moverscore_question_answer_generation_with_gold_answer_gold_answer
            value: 70.07

Model Card of `lmqg/mt5-base-ruquad-qg`

This model is fine-tuned version of google/mt5-base for question generation task on the lmqg/qg_ruquad (dataset_name: default) via lmqg.

Overview

Language model: google/mt5-base
Language: ru
Training data: lmqg/qg_ruquad (default)
Online Demo: https://autoqg.net/
Repository: https://github.com/asahi417/lm-question-generation
Paper: https://arxiv.org/abs/2210.03992

Usage

With lmqg

from lmqg import TransformersQG

# initialize model
model = TransformersQG(language="ru", model="lmqg/mt5-base-ruquad-qg")

# model prediction
questions = model.generate_q(list_context="Нелишним будет отметить, что, развивая это направление, Д. И. Менделеев, поначалу априорно выдвинув идею о температуре, при которой высота мениска будет нулевой, в мае 1860 года провёл серию опытов.", list_answer="в мае 1860 года")

With transformers

from transformers import pipeline

pipe = pipeline("text2text-generation", "lmqg/mt5-base-ruquad-qg")
output = pipe("Нелишним будет отметить, что, развивая это направление, Д. И. Менделеев, поначалу априорно выдвинув идею о температуре, при которой высота мениска будет нулевой, <hl> в мае 1860 года <hl> провёл серию опытов.")

Evaluation

Metric (Question Generation): raw metric file

	Score	Type	Dataset
BERTScore	85.82	default	lmqg/qg_ruquad
Bleu_1	33.04	default	lmqg/qg_ruquad
Bleu_2	26.31	default	lmqg/qg_ruquad
Bleu_3	21.42	default	lmqg/qg_ruquad
Bleu_4	17.63	default	lmqg/qg_ruquad
METEOR	28.48	default	lmqg/qg_ruquad
MoverScore	64.56	default	lmqg/qg_ruquad
ROUGE_L	33.02	default	lmqg/qg_ruquad

Metric (Question & Answer Generation, Reference Answer): Each question is generated from the gold answer. raw metric file

	Score	Type	Dataset
BERTScore	90.95	default	lmqg/qg_ruquad
Bleu_1	47.1	default	lmqg/qg_ruquad
Bleu_2	35.2	default	lmqg/qg_ruquad
Bleu_3	26.68	default	lmqg/qg_ruquad
Bleu_4	19.28	default	lmqg/qg_ruquad
METEOR	45.42	default	lmqg/qg_ruquad
MoverScore	69.57	default	lmqg/qg_ruquad
QAAlignedF1Score (BERTScore)	91.1	default	lmqg/qg_ruquad
QAAlignedF1Score (MoverScore)	70.06	default	lmqg/qg_ruquad
QAAlignedPrecision (BERTScore)	91.11	default	lmqg/qg_ruquad
QAAlignedPrecision (MoverScore)	70.07	default	lmqg/qg_ruquad
QAAlignedRecall (BERTScore)	91.09	default	lmqg/qg_ruquad
QAAlignedRecall (MoverScore)	70.04	default	lmqg/qg_ruquad
ROUGE_L	52.09	default	lmqg/qg_ruquad

Training hyperparameters

The following hyperparameters were used during fine-tuning:

dataset_path: lmqg/qg_ruquad
dataset_name: default
input_types: ['paragraph_answer']
output_types: ['question']
prefix_types: None
model: google/mt5-base
max_length: 512
max_length_output: 32
epoch: 16
batch: 4
lr: 0.0005
fp16: False
random_seed: 1
gradient_accumulation_steps: 16
label_smoothing: 0.15

The full configuration can be found at fine-tuning config file.

Citation

@inproceedings{ushio-etal-2022-generative,
    title = "{G}enerative {L}anguage {M}odels for {P}aragraph-{L}evel {Q}uestion {G}eneration",
    author = "Ushio, Asahi  and
        Alva-Manchego, Fernando  and
        Camacho-Collados, Jose",
    booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, U.A.E.",
    publisher = "Association for Computational Linguistics",
}